The paper deals with the problem of efficient adaptation of speech recognition systems to individual users. The goal is to achieve better performance in specific applications where one known speaker is expected. In our approach we adopt the MAP (Maximum A Posteriori) method for this purpose. The MAP based formulae for the adaptation of the HMM (Hidden Markov Model) parameters are described. Several alternative versions of this method have been implemented and experimentally verified in two areas, first in the isolated-word recognition (IWR) task and later also in the large vocabulary continuous speech recognition (LVCSR) system, both developed for the Czech language. The results show that the word error rate (WER) can be reduced by more than 20% for a speaker who provides tens of words (in case of IWR) or tens of sentences (in case of LVCSR) for the adaptation. Recently, we have used the described methods in the design of two practical applications: voice dictation to a PC and automatic transcription of radio and TV news.
展开▼
